3D 视觉 - arXivDaily 专题

2211.14738 2022-11-29 cs.RO 57%

Distilled Visual and Robot Kinematics Embeddings for Metric Depth Estimation in Monocular Scene Reconstruction

Ruofeng Wei, Bin Li, Hangjie Mo, Fangxun Zhong, Yonghao Long, Qi Dou, Yun-Hui Liu, Dong Sun

专题命中三维重建：3D reconstruction(abstract)；分类 cs.RO

2110.03912 2022-11-29 cs.CV cs.AI eess.IV 57%

Stereo Dense Scene Reconstruction and Accurate Localization for Learning-Based Navigation of Laparoscope in Minimally Invasive Surgery

Ruofeng Wei, Bin Li, Hangjie Mo, Bo Lu, Yonghao Long, Bohan Yang, Qi Dou, Yunhui Liu, Dong Sun

专题命中三维重建：3D reconstruction(abstract)；分类 cs.CV

Journal ref IEEE Transactions on Biomedical Engineering 2022

2110.00990 2022-11-24 cs.CV 57%

Hierarchical Kinematic Probability Distributions for 3D Human Shape and Pose Estimation from Images in the Wild

Akash Sengupta, Ignas Budvytis, Roberto Cipolla

专题命中三维重建：3D reconstruction(abstract)；分类 cs.CV

Comments ICCV 2021 (Edited to reduce file size)

2211.11066 2022-11-22 cs.CV 57%

Hybrid Transformer Based Feature Fusion for Self-Supervised Monocular Depth Estimation

Snehal Singh Tomar, Maitreya Suin, A. N. Rajagopalan

专题命中三维重建：3D vision(abstract)；分类 cs.CV

Comments Presented at the Advances in Image Manipulation Workshop at ECCV 2022

2211.09770 2022-11-18 cs.CV 57%

3DLatNav: Navigating Generative Latent Spaces for Semantic-Aware 3D Object Manipulation

Amaya Dharmasiri, Dinithi Dissanayake, Mohamed Afham, Isuru Dissanayake, Ranga Rodrigo, Kanchana Thilakarathna

专题命中三维重建：point cloud(abstract)；分类 cs.CV

2211.08533 2022-11-17 cs.CV 57%

A Point in the Right Direction: Vector Prediction for Spatially-aware Self-supervised Volumetric Representation Learning

Yejia Zhang, Pengfei Gu, Nishchal Sapkota, Hao Zheng, Peixian Liang, Danny Z. Chen

专题命中三维重建：spatial understanding(abstract)；分类 cs.CV

2208.10937 2022-11-16 eess.IV cs.CV cs.LG 57%

Improving Computed Tomography (CT) Reconstruction via 3D Shape Induction

Elena Sizikova, Xu Cao, Ashia Lewis, Kenny Moise, Megan Coffee

专题命中三维重建：3D reconstruction(abstract)；分类 cs.CV

Comments Extended Abstract presented at Machine Learning for Health (ML4H) symposium 2022, November 28th, 2022, New Orleans, United States & Virtual, http://www.ml4h.cc, 11 pages

2207.08925 2022-11-16 cs.CV cs.LG 57%

Image to Icosahedral Projection for $\mathrm{SO}(3)$ Object Reasoning from Single-View Images

David Klee, Ondrej Biza, Robert Platt, Robin Walters

专题命中三维重建：point cloud(abstract)；分类 cs.CV

2211.07195 2022-11-15 cs.CV 57%

Controllable GAN Synthesis Using Non-Rigid Structure-from-Motion

René Haas, Stella Graßhof, Sami S. Brandt

专题命中三维重建：3D reconstruction(abstract)；分类 cs.CV

2211.06195 2022-11-14 cs.CV cs.AI 57%

HOReeNet: 3D-aware Hand-Object Grasping Reenactment

Changhwa Lee, Junuk Cha, Hansol Lee, Seongyeong Lee, Donguk Kim, Seungryul Baek

专题命中三维重建：3D reconstruction(abstract)；分类 cs.CV

Comments 5 pages, 5 figures

2211.05304 2022-11-11 cs.CV cs.LG 57%

Contrastive Self-Supervised Learning for Skeleton Representations

Nico Lingg, Miguel Sarabia, Luca Zappella, Barry-John Theobald

专题命中三维重建：point cloud(abstract)；分类 cs.CV

Comments 8 pages, 2 figures, 4 tables. Accepted at the NeurIPS 2022 Workshop: Self-Supervised Learning - Theory and Practice

2208.11948 2022-11-07 cs.CV 57%

Learning to Construct 3D Building Wireframes from 3D Line Clouds

Yicheng Luo, Jing Ren, Xuefei Zhe, Di Kang, Yajing Xu, Peter Wonka, Linchao Bao

专题命中三维重建：point cloud(abstract)；分类 cs.CV

Comments 10 pages, 6 figures

2203.15065 2022-11-01 cs.CV 57%

DeepShadow: Neural Shape from Shadow

Asaf Karnieli, Ohad Fried, Yacov Hel-Or

专题命中三维重建：3D reconstruction(abstract)；分类 cs.CV

Comments ECCV 2022. Project page available at https://asafkar.github.io/deepshadow/

2210.15200 2022-10-28 cs.CV cs.AI cs.LG 57%

Deep-MDS Framework for Recovering the 3D Shape of 2D Landmarks from a Single Image

Shima Kamyab, Zohreh Azimifar

专题命中三维重建：3D reconstruction(abstract)；分类 cs.CV

2210.15040 2022-10-28 cs.CV 57%

PERGAMO: Personalized 3D Garments from Monocular Video

Andrés Casado-Elvira, Marc Comino Trinidad, Dan Casas

专题命中三维重建：3D reconstruction(abstract)；分类 cs.CV

Comments Published at Computer Graphics Forum (Proc. of ACM/SIGGRAPH SCA), 2022. Project website http://mslab.es/projects/PERGAMO/

2203.16034 2022-10-26 cs.CV cs.AI cs.LG 57%

Monitored Distillation for Positive Congruent Depth Completion

Tian Yu Liu, Parth Agrawal, Allison Chen, Byung-Woo Hong, Alex Wong

专题命中三维重建：point cloud(abstract)；分类 cs.CV

2210.13079 2022-10-25 cs.CV cs.AI 57%

mm-Wave Radar Hand Shape Classification Using Deformable Transformers

Athmanarayanan Lakshmi Narayanan, Asma Beevi K. T, Haoyang Wu, Jingyi Ma, W. Margaret Huang

专题命中三维重建：point cloud(abstract)；分类 cs.CV

2210.12856 2022-10-25 cs.CV cs.AI 57%

Symmetry and Variance: Generative Parametric Modelling of Historical Brick Wall Patterns

Sevgi Altun, Mustafa Cem Gunes, Yusuf H. Sahin, Alican Mertan, Gozde Unal, Mine Ozkar

专题命中三维重建：point cloud(abstract)；分类 cs.CV

Comments 10 pages, 7 Figures. This paper is published at "Symmetry: Art and Science | 12th SIS-Symmetry Congress"

Journal ref Porto, Portugal: SIS-Symmetry (2022) pp. 96-104

2210.11467 2022-10-21 cs.CV 57%

Multi-View Guided Multi-View Stereo

Matteo Poggi, Andrea Conti, Stefano Mattoccia

专题命中三维重建：3D reconstruction(abstract)；分类 cs.CV

Comments IROS 2022. First two authors contributed equally. Project page: https://github.com/andreaconti/multi-view-guided-multi-view-stereo

2208.01685 2022-10-20 cs.GR 57%

Differentiable Subdivision Surface Fitting

Tianhao Xie

专题命中三维重建：point cloud(abstract)；分类 cs.GR

2207.00182 2022-10-20 cs.CV 57%

Recovering Detail in 3D Shapes Using Disparity Maps

Marissa Ramirez de Chanlatte, Matheus Gadelha, Thibault Groueix, Radomir Mech

专题命中三维重建：point cloud(abstract)；分类 cs.CV

2205.13914 2022-10-19 cs.CV 57%

3DILG: Irregular Latent Grids for 3D Generative Modeling

Biao Zhang, Matthias Nießner, Peter Wonka

专题命中三维重建：point cloud(abstract)；分类 cs.CV

Comments Accepted at NeurIPS 2022. Project page: https://1zb.github.io/3DILG

2210.09148 2022-10-18 cs.CV 57%

Pruning-based Topology Refinement of 3D Mesh using a 2D Alpha Mask

Gaëtan Landreau, Mohamed Tamaazousti

专题命中三维重建：3D reconstruction(abstract)；分类 cs.CV

Comments 11 pages ; published at ISVC,Oral - 2022

2206.01724 2022-10-18 cs.CV cs.AI 57%

SNAKE: Shape-aware Neural 3D Keypoint Field

Chengliang Zhong, Peixing You, Xiaoxue Chen, Hao Zhao, Fuchun Sun, Guyue Zhou, Xiaodong Mu, Chuang Gan, Wenbing Huang

专题命中三维重建：point cloud(abstract)；分类 cs.CV

Comments Accepted by NeurIPS 2022. Codes are available at https://github.com/zhongcl-thu/SNAKE

2206.13597 2022-10-18 cs.CV 57%

NeuRIS: Neural Reconstruction of Indoor Scenes Using Normal Priors

Jiepeng Wang, Peng Wang, Xiaoxiao Long, Christian Theobalt, Taku Komura, Lingjie Liu, Wenping Wang

专题命中三维重建：3D reconstruction(abstract)；分类 cs.CV

2107.00511 2022-10-18 cs.RO 57%

TransSC: Transformer-based Shape Completion for Grasp Evaluation

Wenkai Chen, Hongzhuo Liang, Zhaopeng Chen, Fuchun Sun, Jianwei Zhang

专题命中三维重建：point cloud(abstract)；分类 cs.RO

Journal ref Journal of Intelligent & Robotic Systems (2022) 104: 45

2206.00665 2022-10-13 cs.CV 57%

MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstruction

Zehao Yu, Songyou Peng, Michael Niemeyer, Torsten Sattler, Andreas Geiger

专题命中三维重建：3D reconstruction(abstract)；分类 cs.CV

Comments Project page: https://niujinshuchong.github.io/monosdf/

2210.05517 2022-10-12 cs.CV 57%

DeepMLE: A Robust Deep Maximum Likelihood Estimator for Two-view Structure from Motion

Yuxi Xiao, Li Li, Xiaodi Li, Jian Yao

专题命中三维重建：3D reconstruction(abstract)；分类 cs.CV

Comments 8 pages, Accepted by IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS2022)

2210.05250 2022-10-12 cs.GR cs.NA math.NA 57%

Digital twins for city simulation: Automatic, efficient, and robust mesh generation for large-scale city modeling and simulation

Vasilis Naserentin, Anders Logg

专题命中三维重建：point cloud(abstract)；分类 cs.GR

2210.03158 2022-10-10 cs.CV cs.AI 57%

Neural Volumetric Mesh Generator

Yan Zheng, Lemeng Wu, Xingchao Liu, Zhen Chen, Qiang Liu, Qixing Huang

专题命中三维重建：point cloud(abstract)；分类 cs.CV

1. 三维重建 4398 篇

Distilled Visual and Robot Kinematics Embeddings for Metric Depth Estimation in Monocular Scene Reconstruction

Stereo Dense Scene Reconstruction and Accurate Localization for Learning-Based Navigation of Laparoscope in Minimally Invasive Surgery

Hierarchical Kinematic Probability Distributions for 3D Human Shape and Pose Estimation from Images in the Wild

Hybrid Transformer Based Feature Fusion for Self-Supervised Monocular Depth Estimation

3DLatNav: Navigating Generative Latent Spaces for Semantic-Aware 3D Object Manipulation

A Point in the Right Direction: Vector Prediction for Spatially-aware Self-supervised Volumetric Representation Learning

Improving Computed Tomography (CT) Reconstruction via 3D Shape Induction

Image to Icosahedral Projection for $\mathrm{SO}(3)$ Object Reasoning from Single-View Images

Controllable GAN Synthesis Using Non-Rigid Structure-from-Motion

HOReeNet: 3D-aware Hand-Object Grasping Reenactment

Contrastive Self-Supervised Learning for Skeleton Representations

Learning to Construct 3D Building Wireframes from 3D Line Clouds

DeepShadow: Neural Shape from Shadow

Deep-MDS Framework for Recovering the 3D Shape of 2D Landmarks from a Single Image

PERGAMO: Personalized 3D Garments from Monocular Video

Monitored Distillation for Positive Congruent Depth Completion

mm-Wave Radar Hand Shape Classification Using Deformable Transformers

Symmetry and Variance: Generative Parametric Modelling of Historical Brick Wall Patterns

Multi-View Guided Multi-View Stereo

Differentiable Subdivision Surface Fitting

Recovering Detail in 3D Shapes Using Disparity Maps

3DILG: Irregular Latent Grids for 3D Generative Modeling

Pruning-based Topology Refinement of 3D Mesh using a 2D Alpha Mask

SNAKE: Shape-aware Neural 3D Keypoint Field

NeuRIS: Neural Reconstruction of Indoor Scenes Using Normal Priors

TransSC: Transformer-based Shape Completion for Grasp Evaluation

MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstruction

DeepMLE: A Robust Deep Maximum Likelihood Estimator for Two-view Structure from Motion

Digital twins for city simulation: Automatic, efficient, and robust mesh generation for large-scale city modeling and simulation

Neural Volumetric Mesh Generator